Vision-aided grasp classification: design and evaluation of compact CNN for prosthetic hands.

Powered prosthetic hands capable of executing various grasp patterns are highly sought-after solutions for upper limb amputees. A crucial requirement for such prosthetic hands is the accurate identification of the intended grasp pattern and subsequent activation of the prosthetic digits accordingly. Vision-based grasp classification techniques offer improved coordination between amputees and prosthetic hands without physical contact. Deep learning methods, particularly Convolutional Neural Networks (CNNs), are utilized to process visual information for classification. The key challenge lies in developing a model that can effectively generalize across various object shapes and accurately classify grasp classes. To address this, a compact CNN model named GraspCNet is proposed, specifically designed for grasp classification in prosthetic hands. The use of separable convolutions reduces the computational burden, making it potentially suitable for real-time applications on embedded systems. The GraspCNet model is designed to learn and generalize from object shapes, allowing it to effectively classify unseen objects beyond those included in the training dataset. The proposed model was trained and tested using various standard object data sets. A cross-validation strategy has been adopted to perform better in seen and unseen object class scenarios. The average accuracy achieved was 82.22% and 75.48% in the case of seen, and unseen object classes respectively. In computer-based real-time experiments, the GraspCNet model achieved an accuracy of 69%. A comparative analysis with state-of-the-art techniques revealed that the proposed GraspCNet model outperformed most benchmark techniques and demonstrated comparable performance with the DcnnGrasp method. The compact nature of the GraspCNet model suggests its potential for integration with other sensing modalities in prosthetic hands.

Weathering the crash: Do customer-company relationships pay off during economic crises?

Do stronger relationships with customers (customer-company relationships [CCR]) help firms better weather economic crises? To answer this question, we examine firm performance during the stock market crashes associated with the two most severe economic crises of the last 15 years-the protracted Great Recession crisis (2008-2009) and the shorter but extreme COVID-19 pandemic crisis (2020). Juxtaposing the predominant expected utility theory perspective with observed deviations in investor behavior during crises, we find that both pre-crash firm-level customer satisfaction and customer loyalty are positively associated with abnormal stock returns and lower idiosyncratic risk during a market crash, while pre-crash firm-level customer complaint rate negatively affects abnormal stock returns and increases idiosyncratic risk. On average, we find that one standard deviation higher CCR is associated with between $0.9 billion and $2.4 billion in market capitalization on an annualized basis. Importantly, we find that these effects are weaker for firms with higher market share during the COVID-19 crash, but not during the Great Recession crash. These results are found to be robust to a variety of alternate model specifications, time periods, sub-samples, accounting for firm strategies during the crises, and endogeneity corrections. When compared to relevant non-crash periods, we also find that such effects are equally strong during the Great Recession crash and even stronger during the COVID-19 pandemic crash. Contributing to both the marketing-finance interface literature and the nascent literature on marketing during economic crises, implications from these findings are provided for researchers, marketing theory, and managers. Supplementary information: The online version contains supplementary material available at 10.1007/s11747-023-00947-1.

The American Customer Satisfaction Index (ACSI): A sample dataset and description.

This article provides a sample of survey data collected by the American Customer Satisfaction Index (ACSI). Using online sampling and stratified interviewing techniques of actual customers of predominantly large market-share ("large cap") companies, the ACSI annually collects data from some 400,000 consumers residing across the United States for more than 400 companies within about 50 consumer industries. For this article and the data depository, consumers' perceptions of their experiences with individual companies included within four consumer industries as defined and measured by ACSI - processed food, commercial airlines, Internet service providers, and commercial banks - are included in the dataset. These industries were chosen to represent and illustrate a cross-section of data from differentiated sectors, not because they are representative of the larger economy or larger ACSI dataset per se. The survey items reflect a diverse array of customers' perceptions regarding prior expectations, perceived quality, perceived value, customer satisfaction, complaint behavior, and customer loyalty. These are also the core latent factors modeled in the so-called ACSI model since 1994. The ACSI model is continuously analyzed using a proprietary and patented Partial Least Squares structural equation modeling approach (PLS-SEM). Detailed firm- or brand-level results from the ACSI data are used by individual companies for strategic organizational decision-making and in the aggregate to forecast trends in the U.S. national economy. ACSI data have been analyzed in thousands of peer-reviewed academic and practitioner journal articles.

GourmetNet: Food Segmentation Using Multi-Scale Waterfall Features with Spatial and Channel Attention.

We propose GourmetNet, a single-pass, end-to-end trainable network for food segmentation that achieves state-of-the-art performance. Food segmentation is an important problem as the first step for nutrition monitoring, food volume and calorie estimation. Our novel architecture incorporates both channel attention and spatial attention information in an expanded multi-scale feature representation using our advanced Waterfall Atrous Spatial Pooling module. GourmetNet refines the feature extraction process by merging features from multiple levels of the backbone through the two attention modules. The refined features are processed with the advanced multi-scale waterfall module that combines the benefits of cascade filtering and pyramid representations without requiring a separate decoder or post-processing. Our experiments on two food datasets show that GourmetNet significantly outperforms existing current state-of-the-art methods.

Genetic homogeneity revealed in micropropagated Bauhinia racemosa Lam. using gene targeted markers CBDP and SCoT.

Two gene targeted markers i.e. CAAT box-derived polymorphism (CBDP) and start codon targeted (SCoT) polymorphism were applied to analyze the genetic stability of in vitro propagated plants of Bauhinia racemosa Lam. multiplied by enhanced axillary shoot proliferation of mature tree derived nodal explant. Nine randomly selected micropropagated plants of 1 year age were subjected to molecular analysis. The isolated genomic DNA samples were subjected to PCR amplification with a total of 61 primers (25 CBDP and 36 SCoT) out of which 39 primers (21 CBDP and 18 SCoT) produced scorable amplicons. A total of 97 and 88 clear, distinct and reproducible amplicons were produced by CBDP and SCoT primers, respectively. The monomorphic banding pattern obtained through all the tested primers corroborated the true to type nature of in vitro propagated plants of B. racemosa.

Aeroponics for adventitious rhizogenesis in evergreen haloxeric tree Tamarix aphylla (L.) Karst.: influence of exogenous auxins and cutting type.

Tamarix aphylla (L.) Karst., a drought resistant halophyte tree, is an agroforestry species which can be used for reclamation of waterlogged saline and marginal lands. Due to very low seed viability and unsuitable conditions for seed germination, the tree is becoming rare in Indian Thar desert. Present study concerns the evaluation of aeroponics technique for vegetative propagation of T. aphylla. Effect of various exogenous auxins (indole-3-acetic acid, indole-3-butyric acid, naphthalene acetic acid) at different concentrations (0.0, 1.0, 2.0, 3.0, 5.0, 10.0 mg l-1) was examined for induction of adventitious rooting and other morphological features. Among all three auxins tested individually, maximum rooting response (79%) was observed with IBA 2.0 mg l-1. However, stem cuttings treated with a combination of auxins (2.0 mg l-1 IBA and 1.0 mg l-1 IAA) for 15 min resulted in 87% of rooting response. Among three types of stem cuttings (apical shoot, newly sprouted cuttings, mature stem cuttings), maximum rooting (~ 90%) was observed on mature stem cuttings. Number of roots and root length were significantly higher in aeroponically rooted stem cuttings as compared to stem cuttings rooted in soil conditions. Successfully rooted and sprouted plants were transferred to polybags with 95% survival rate. This is the first report on aeroponic culture of Tamarix aphylla which can be utilized in agroforestry practices, marginal land reclamation and physiological studies.

In vitro propagation, ex vitro rooting and leaf micromorphology of Bauhinia racemosa Lam.: a leguminous tree with medicinal values.

A micropropagation system for Bauhinia racemosa Lam. was developed involving axillary shoot proliferation and ex vitro rooting using nodal explants obtained from mature tree. MS medium with 3.0 mg l-1 BA (6-benzyladenine) was optimum for shoot bud induction. For shoot multiplication, mother explants were transferred repeatedly on medium containing low concentration of BA (0.75 mg l-1). Number of shoots was increased up to two passages and decreased thereafter. Shoot multiplication was further enhanced on MS medium containing 0.25 mg l-1 each of BA and Kin (Kinetin) with 0.1 mg l-1 of NAA (α-naphthalene acetic acid). Addition of 0.004 mg l-1 TDZ (thidiazuron) increased the rate of shoot multiplication and 21.81 ± 1.26 shoots per culture vessel were obtained. In vitro regenerated shoots were rooted under ex vitro conditions treated with 400 mg l-1 IBA (indole-3-butyric acid) for 7 min on sterile soilrite. After successful hardening in greenhouse, ex vitro rooted plants were transferred to the field conditions with ≈85% of survival rate. Micromorphological changes were observed on leaf surface i.e. development of vein density and trichomes and stomatal appearance, when plants were subjected to environmental conditions. This is the first report on in vitro regeneration of B. racemosa from mature tree.